Spaces:
Sleeping
Sleeping
| import pandas as pd | |
| import numpy as np | |
| from sklearn.model_selection import train_test_split, GridSearchCV | |
| from sklearn.linear_model import SGDClassifier | |
| from sklearn.metrics import classification_report, confusion_matrix, make_scorer, f1_score | |
| import shap | |
| import xgboost as xgb | |
| import gradio as gr | |
| import matplotlib.pyplot as plt | |
| import joblib | |
| SVM = joblib.load('SVM.pkl') | |
| Log_Reg = joblib.load('Log_Reg.pkl') | |
| XGB = xgb.XGBClassifier() | |
| XGB.load_model('XGB.model') | |
| df = pd.read_csv('Superstore.csv') | |
| df.dropna(subset=["Region", "Category", "Sub-Category", "Quantity", "Discount"], inplace=True) | |
| MEDIAN = 8.662 # from the exploratory analysis file | |
| RANDOM_STATE = 42 # random seed to ensure results are reproducible | |
| region=np.unique(df['Region'], return_inverse=True)[1] | |
| category=np.unique(df['Category'], return_inverse=True)[1] | |
| subCategory=np.unique(df['Sub-Category'], return_inverse=True)[1] | |
| # turn quantity, discount, and profit columns into vectors of numbers | |
| quantity = df["Quantity"].to_numpy() | |
| discount = df["Discount"].to_numpy() | |
| profit = df["Profit"].to_numpy() | |
| vectorizedDataset = np.empty((len(region), 5)) | |
| labels = np.empty(len(region)) | |
| # generate feature vectors | |
| for i in range(0, len(region)): | |
| data = np.zeros((1, 5)) | |
| data[0][0] = region[i] | |
| data[0][1] = category[i] | |
| data[0][2] = subCategory[i] | |
| data[0][3] = quantity[i] | |
| data[0][4] = discount[i] | |
| vectorizedDataset[i] = data | |
| if (profit[i] > MEDIAN): | |
| labels[i] = 1 | |
| else: | |
| labels[i] = 0 | |
| train, test, trainLabels, testLabels = train_test_split(vectorizedDataset, labels, test_size=0.3, random_state=RANDOM_STATE) | |
| region_label = {'Central': 0, 'East': 1, 'South': 2, 'West': 3} | |
| category_label = {'Furniture': 0, 'Office Supplies': 1, 'Technology': 2} | |
| sub_category_label = {'Accessories': 0, 'Appliances': 1, 'Art': 2, 'Binders': 3, 'Bookcases': 4, | |
| 'Chairs': 5, 'Copiers': 6, 'Envelopes': 7, 'Fasteners': 8, 'Furnishings': 9, | |
| 'Labels': 10, 'Machines': 11, 'Paper': 12, 'Phones': 13, 'Storage': 14, 'Supplies': 15, | |
| 'Tables': 16} | |
| profit_label = {0: 'Below Median Profit', 1: 'Above Median Profit'} | |
| feature_names = ["Region", "Category", "Sub-Category", "Quantity", "Discount"] | |
| def sanitize_inputs(Region, Category, Sub_Category, Quantity, Discount): | |
| try: | |
| Region = region_label[Region] | |
| Category = category_label[Category] | |
| Sub_Category = sub_category_label[Sub_Category] | |
| except KeyError: | |
| return ["Please provide region, category, and sub category from the pre-defined Superstore dataset classes", None] | |
| if Quantity < 1 or Discount < 0: | |
| return ["Quantity and Discount must be positive", None] | |
| if not isinstance(Quantity, int): | |
| return ["Quantity must be an integer", None] | |
| if Discount > 1: | |
| return ["Discount cannot be greater than one", None] | |
| return [Region, Category, Sub_Category] | |
| def XGB_predict(Region, Category, Sub_Category, Quantity, Discount): | |
| sanitized = sanitize_inputs(Region, Category, Sub_Category, Quantity, Discount) | |
| if len(sanitized)==2: | |
| return sanitized | |
| input = np.array([[sanitized[0], sanitized[1], sanitized[2], Quantity, Discount]]) | |
| predicted_class = XGB.predict(input) | |
| explainer = shap.Explainer(XGB, test) | |
| shap_values = explainer(input) | |
| shap_values.feature_names = ["Region", "Category", "Sub-Category", "Quantity", "Discount"] | |
| plot = shap.plots.bar(shap_values, show=False) | |
| plt.savefig('shap_plot_XGB.png') | |
| return [profit_label[predicted_class[0]], 'shap_plot_XGB.png'] | |
| def SVM_predict(Region, Category, Sub_Category, Quantity, Discount): | |
| sanitized = sanitize_inputs(Region, Category, Sub_Category, Quantity, Discount) | |
| if len(sanitized)==2: | |
| return sanitized | |
| input = np.array([[sanitized[0], sanitized[1], sanitized[2], Quantity, Discount]]) | |
| predicted_class = SVM.predict(input) | |
| explainer = shap.Explainer(SVM, test) | |
| shap_values = explainer(input) | |
| shap_values.feature_names = ["Region", "Category", "Sub-Category", "Quantity", "Discount"] | |
| plot = shap.plots.bar(shap_values, show=False) | |
| plt.savefig('shap_plot_SVM.png') | |
| return [profit_label[predicted_class[0]], 'shap_plot_SVM.png'] | |
| def Log_reg_predict(Region, Category, Sub_Category, Quantity, Discount): | |
| sanitized = sanitize_inputs(Region, Category, Sub_Category, Quantity, Discount) | |
| if len(sanitized)==2: | |
| return sanitized | |
| input = np.array([[sanitized[0], sanitized[1], sanitized[2], Quantity, Discount]]) | |
| predicted_class = Log_Reg.predict(input) | |
| explainer = shap.Explainer(Log_Reg, test) | |
| shap_values = explainer(input) | |
| shap_values.feature_names = ["Region", "Category", "Sub-Category", "Quantity", "Discount"] | |
| plot = shap.plots.bar(shap_values, show=False) | |
| plt.savefig('shap_plot_LogReg.png') | |
| return [profit_label[predicted_class[0]], 'shap_plot_LogReg.png'] | |
| LogReg_tab = gr.Interface( | |
| fn=Log_reg_predict, | |
| inputs=["text", "text", "text", "number", "number"], | |
| outputs=[ | |
| gr.Label(label="Model Prediction"), | |
| gr.Image(label="Shapley Values"), | |
| ], | |
| title="Logistic Regression Profit Prediction", | |
| description="Create your own purchases and see if the Logistic Regression model predicts they will make above or below the median profit\n\nValid regions: ['Central', 'East', 'South', 'West']\n\nValid product categories: ['Furniture', 'Office Supplies', 'Technology']\n\nValid product sub-categories: ['Accessories', 'Appliances', 'Art', 'Binders', 'Bookcases', 'Chairs', 'Copiers', 'Envelopes', 'Fasteners', 'Furnishings', 'Labels', 'Machines', 'Paper', 'Phones', 'Storage', 'Supplies', 'Tables']", | |
| ) | |
| SVM_tab = gr.Interface( | |
| fn=SVM_predict, | |
| inputs=["text", "text", "text", "number", "number"], | |
| outputs=[ | |
| gr.Label(label="Model Prediction"), | |
| gr.Image(label="Shapley Values"), | |
| ], | |
| title="SVM Profit Prediction", | |
| description="Create your own purchases and see if the SVM model predicts they will make above or below the median profit\n\nValid regions: ['Central', 'East', 'South', 'West']\n\nValid product categories: ['Furniture', 'Office Supplies', 'Technology']\n\nValid product sub-categories: ['Accessories', 'Appliances', 'Art', 'Binders', 'Bookcases', 'Chairs', 'Copiers', 'Envelopes', 'Fasteners', 'Furnishings', 'Labels', 'Machines', 'Paper', 'Phones', 'Storage', 'Supplies', 'Tables']", | |
| ) | |
| XGB_tab = gr.Interface( | |
| fn=XGB_predict, | |
| inputs=["text", "text", "text", "number", "number"], | |
| outputs=[ | |
| gr.Label(label="Model Prediction"), | |
| gr.Image(label="Shapley Values"), | |
| ], | |
| title="XGB Profit Prediction", | |
| description="Create your own purchases and see if the XGB model predicts they will make above or below the median profit\n\nValid regions: ['Central', 'East', 'South', 'West']\n\nValid product categories: ['Furniture', 'Office Supplies', 'Technology']\n\nValid product sub-categories: ['Accessories', 'Appliances', 'Art', 'Binders', 'Bookcases', 'Chairs', 'Copiers', 'Envelopes', 'Fasteners', 'Furnishings', 'Labels', 'Machines', 'Paper', 'Phones', 'Storage', 'Supplies', 'Tables']", | |
| ) | |
| demo = gr.TabbedInterface([LogReg_tab, SVM_tab, XGB_tab], tab_names=["Logistic Regression", "SVM", "XGB"], theme=gr.themes.Soft()) | |
| demo.launch(debug=True) |